Research And Analysis Of Long-term Power Load Forecasting

Electric Load forecasting is an important task of power utilities.It is the important foundation of the study on electric system planning problem, economical running. The accurate prediction of electric load is significant to the national economic development and the safe economical operation of power system.The long-term power load forecasting various ways, Due to the influence factors of the load forecast of diversity, Without a fixed method can follow, So, there was a variety of adapt to different situation forecast method, Each prediction models have their application scope. Consider multiple method of influence factors, the modeling's predicted results have more rich connotation, The prediction model than single factor considered more comprehensive, more system, So can effectively reduce prediction model process some environment of the influence of random factor, so as to improve the prediction accuracy.Based on the optimization of grey model study, Combined with the characteristics of electric power load forecasting medium-term. From 1996 to 2009 in Shandong province of power consumption, to research the characteristics of this instance, Comprehensive find a kind optimization grey forecasting model. After and traditional grey forecasting model contrast, precision improved. In view of the above methods do not consider related factors. For this example this paper and using principal component analysis method to establish mathematical model, For example, the characteristic analysis found. Because the correlation between each factors is too strong, using principal component analysis modeling unfavorable, So put forward a new method of image trend choice method. Through the actual value and with the value of the grey prediction model is also explain image contrast, the choice method screening variable trend method are reasonable.Finally, this paper apply optimized grey model to predict the data of various influential factors of 2010 ~ 2015, they will capture component analysis model of the generation, predict 2010 ~ 2015 years of load value, it is only for reference. With two kinds of prediction method in this paper, analyzes the advantages and disadvantages of two prediction method in the research process, and through the experience in the medium and long term power load forecasting method for future development of this paper gives some suggestions.